© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108336
    Prev
    Next
    INDEX
    Explanations

    falling for something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loud
    -0.08
    Emitter
    -0.07
    揣
    -0.07
    _SUR
    -0.07
     Fitness
    -0.07
     labeled
    -0.07
    _UINT
    -0.06
     emerging
    -0.06
     Gtk
    -0.06
    modes
    -0.06
    POSITIVE LOGITS
    Impossible
    0.07
    /il
    0.07
    ほしい
    0.07
    可能な
    0.07
    רכה
    0.07
    된다
    0.07
    _pll
    0.06
    .progressBar
    0.06
     Lives
    0.06
    inki
    0.06
    Activations Density 0.052%

    No Known Activations