© 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 EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 75914
    Prev
    Next
    INDEX
    Explanations

    consequence

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >/
    -0.08
     del
    -0.08
    잖아요
    -0.07
    等特点
    -0.07
    铢
    -0.07
     �
    -0.07
    .widgets
    -0.07
     dalla
    -0.07
    _median
    -0.07
    괌
    -0.07
    POSITIVE LOGITS
    HAVE
    0.08
    iste
    0.07
     לכ
    0.07
    uctor
    0.07
    Life
    0.07
     fsm
    0.07
    lf
    0.07
    iface
    0.07
    iber
    0.07
    殡
    0.07
    Activations Density 0.152%

    No Known Activations