© 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. 15-RESID-POST-AA
    11. 16760
    Prev
    Next
    INDEX
    Explanations

    residue and waste

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    펜
    -0.07
     THEORY
    -0.07
    .write
    -0.07
     QUICK
    -0.07
     OM
    -0.07
    מכר
    -0.07
     PROGMEM
    -0.07
    légi
    -0.07
    _LEN
    -0.07
    лемент
    -0.06
    POSITIVE LOGITS
    udit
    0.08
     ثم
    0.08
     founders
    0.08
    eos
    0.07
    ')[
    0.07
    	s
    0.07
    .Flags
    0.07
    خلف
    0.07
    -form
    0.07
     [[
    0.06
    Activations Density 0.081%

    No Known Activations