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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 68491
    Prev
    Next
    INDEX
    Explanations

    width

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    3
    -0.07
    اه
    -0.07
    iosis
    -0.06
     []).
    -0.06
    صاص
    -0.06
     resonance
    -0.06
    起了
    -0.06
    -I
    -0.06
     reef
    -0.06
     foolish
    -0.06
    POSITIVE LOGITS
    Width
    0.09
    TextWriter
    0.08
    width
    0.08
     width
    0.07
    .width
    0.07
    蕗
    0.07
    ẅ
    0.07
    莝
    0.07
    raised
    0.07
     Hã
    0.07
    Activations Density 0.019%

    No Known Activations