© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 68925
    Prev
    Next
    INDEX
    Explanations

    substance/stance

    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
    	img
    -0.07
    _radi
    -0.07
     ep
    -0.07
    callbacks
    -0.07
    acao
    -0.07
    elim
    -0.06
     Kor
    -0.06
     thiên
    -0.06
    改良
    -0.06
     monitor
    -0.06
    POSITIVE LOGITS
    -sheet
    0.08
     blends
    0.08
     substances
    0.08
     acquainted
    0.07
    请
    0.07
     şöyle
    0.07
     wink
    0.07
    架子
    0.07
    genes
    0.07
    עשר
    0.07
    Activations Density 0.012%

    No Known Activations