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. 71022
    Prev
    Next
    INDEX
    Explanations

    raw data

    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
    ;-
    -0.07
    ISP
    -0.07
     einzel
    -0.07
    有很大的
    -0.07
    ⛧
    -0.07
     catcher
    -0.07
     Bh
    -0.06
     resembling
    -0.06
    ras
    -0.06
    벘
    -0.06
    POSITIVE LOGITS
     drives
    0.07
    Foreground
    0.07
    敉
    0.07
     limits
    0.07
    .paths
    0.07
     Barclays
    0.07
    给出了
    0.06
     المملكة
    0.06
    prefs
    0.06
    stone
    0.06
    Activations Density 0.021%

    No Known Activations