Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8516
    Prev
    Next
    INDEX
    Explanations

    colons

    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
    𝚣
    -0.07
    夯实
    -0.07
    Calibri
    -0.06
    -item
    -0.06
    帏
    -0.06
    colon
    -0.06
    -context
    -0.06
    pto
    -0.06
    hta
    -0.06
     Byte
    -0.06
    POSITIVE LOGITS
     sniff
    0.08
     confinement
    0.08
    #[
    0.07
     communications
    0.07
     Firestore
    0.07
    تركيز
    0.07
     folding
    0.06
     Fare
    0.06
     mod
    0.06
    Exists
    0.06
    Activations Density 0.000%

    No Known Activations