© 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. 75755
    Prev
    Next
    INDEX
    Explanations

    Given

    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
    plr
    -0.07
    …I
    -0.07
    acje
    -0.07
     vitae
    -0.07
     clarify
    -0.07
     clinging
    -0.07
    _MATERIAL
    -0.07
    _SOFT
    -0.07
    IDS
    -0.07
    POSITIVE LOGITS
    万象
    0.07
    考察
    0.07
     организ
    0.07
    getInstance
    0.06
     الاول
    0.06
     Spo
    0.06
     dp
    0.06
     matchmaking
    0.06
    \$
    0.06
     mon
    0.06
    Activations Density 0.000%

    No Known Activations