INDEX

Explanations

harmful substances/chemicals

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

å®ĮåĸĦ

-0.27

 Mens

-0.26

agan

-0.26

dee

-0.26

aden

-0.25

ely

-0.25

ace

-0.25

äº¬

-0.24

ffa

-0.24

 pieces

-0.24

POSITIVE LOGITS

èĬ½

0.29

wort

0.28

æĵ¦

0.28

çľŁäºº

0.26

razy

0.25

æĤ²

0.25

Son

0.25

court

0.24

.addAttribute

0.24

minster

0.24

Activations Density 0.003%

harmful substances/chemicals

No Comments

No Known Activations