© 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. 75842
    Prev
    Next
    INDEX
    Explanations

    a

    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
     décision
    -0.07
    AAD
    -0.07
    acd
    -0.07
    .intersection
    -0.07
     tamp
    -0.07
    	cat
    -0.07
    crast
    -0.07
    listen
    -0.07
     douche
    -0.07
     או
    -0.07
    POSITIVE LOGITS
     OTHERWISE
    0.07
    同心
    0.07
     seventeen
    0.07
    本场比赛
    0.06
    enders
    0.06
    -res
    0.06
    きっと
    0.06
    泰
    0.06
    更是
    0.06
    Security
    0.06
    Activations Density 0.000%

    No Known Activations