INDEX

Explanations

file paths

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 wake

-0.28

çĿģå¼Ģ

-0.27

 Wake

-0.26

æīĵæĸŃ

-0.26

åħ¬åı¸å°Ĩ

-0.26

å¼¯æĽ²

-0.26

å¼¯

-0.25

bows

-0.25

æľ¬äºº

-0.25

holder

-0.25

POSITIVE LOGITS

çĪ¬

0.28

icted

0.26

olare

0.25

-trade

0.24

-cond

0.24

 organized

0.24

 appetite

0.24

 beaten

0.24

SimpleName

0.24

è´¸

0.24

Activations Density 0.018%

file paths

No Comments

No Known Activations