INDEX

Explanations

comparisons

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

_splits

-0.27

æ¾Ħæ¸ħ

-0.27

enville

-0.26

inton

-0.25

hta

-0.25

.UTF

-0.25

uppe

-0.24

.Locale

-0.24

.mods

-0.24

Îļ

-0.24

POSITIVE LOGITS

ELY

0.27

 hero

0.26

warf

0.26

ç¡Ĵ

0.26

 legend

0.26

legend

0.25

 heroic

0.25

Recv

0.25

 alloy

0.25

-hero

0.24

Activations Density 0.001%

comparisons

No Comments

No Known Activations