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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 88678
    Prev
    Next
    INDEX
    Explanations

    are

    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
    holiday
    -0.09
    Dating
    -0.07
    无助
    -0.07
    吻
    -0.07
    orate
    -0.07
    tokenId
    -0.07
    multiply
    -0.07
    Gay
    -0.07
     setType
    -0.07
    ymax
    -0.07
    POSITIVE LOGITS
     Rick
    0.07
     chắn
    0.07
    ам
    0.07
    	On
    0.06
     WHERE
    0.06
    �
    0.06
    .Sync
    0.06
    ⍣
    0.06
    ognito
    0.06
    (params
    0.06
    Activations Density 0.001%

    No Known Activations