INDEX

Explanations

incidence

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

ft

-0.27

Nullable

-0.25

dling

-0.25

bot

-0.25

apest

-0.25

èģĶç¤¾

-0.25

åĢŁåĬ©

-0.25

çħ´

-0.25

 stress

-0.25

éģĩ

-0.25

POSITIVE LOGITS

 Cran

0.28

sites

0.27

rello

0.26

<Scalar

0.25

 Ð°Ð²Ð³ÑĥÑģÑĤÐ°

0.24

 Mixer

0.24

scar

0.24

æľĪåºķ

0.23

è¿ĩåħ³

0.23

 fauc

0.23

Activations Density 0.791%

incidence

No Comments

No Known Activations