INDEX

Explanations

technical and geographic contexts

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

 Conse

-0.27

 fran

-0.26

éħ¢

-0.25

æ¸¤

-0.25

 GetMessage

-0.25

 consegu

-0.24

atern

-0.24

ParticleSystem

-0.24

unas

-0.24

 spelled

-0.24

POSITIVE LOGITS

çĦĺ

0.28

.charCodeAt

0.27

äº²è¿ĳ

0.27

oko

0.24

éĤ£ä¹Īç®Ģåįķ

0.24

ä¸Ģæīĭ

0.24

å²ģä»¥ä¸Ĭ

0.24

iddles

0.24

annah

0.24

 Definitions

0.24

Activations Density 0.001%

technical and geographic contexts

No Comments

No Known Activations