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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    6. 21268
    Prev
    Next
    INDEX
    Explanations

    Radio broadcasting

    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
    edBy
    -0.07
    .destination
    -0.07
    .Annotations
    -0.07
    AndUpdate
    -0.07
     '",
    -0.07
    ivant
    -0.07
    akhstan
    -0.06
    햤
    -0.06
    ownik
    -0.06
    NotSupportedException
    -0.06
    POSITIVE LOGITS
     premiums
    0.07
     debts
    0.07
     Queen
    0.06
    _eff
    0.06
    ]))
    ↵
    0.06
     Scotch
    0.06
    .openg
    0.06
     Coil
    0.06
     Preview
    0.06
     Scout
    0.06
    Activations Density 0.011%

    No Known Activations