INDEX

Explanations

divine or religious

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

oral

-0.31

ensburg

-0.26

otive

-0.26

æľ¬æĬ¥

-0.25

íķ´ì£¼

-0.25

Gov

-0.25

arge

-0.25

etak

-0.24

 Serial

-0.24

 coch

-0.24

POSITIVE LOGITS

æĺĻ

0.27

éħįæĸĻ

0.25

_ctl

0.25

á»ĥn

0.24

ardo

0.23

æī§

0.23

FTA

0.23

kker

0.23

obbies

0.23

ãĤ«ãĥ¼

0.23

Activations Density 0.001%

divine or religious

No Comments

No Known Activations