INDEX

Explanations

business and legal text snippets

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

èĮħ

-0.26

doch

-0.26

enge

-0.25

 jÃ³

-0.25

_oc

-0.25

å¥½

-0.25

moth

-0.25

æµģç¨ĭ

-0.24

ç©¿

-0.24

bit

-0.23

POSITIVE LOGITS

odyn

0.27

 embarrassing

0.27

 encount

0.26

.Keys

0.25

 embar

0.25

ä¼¼ä¹İæĺ¯

0.25

ByID

0.24

Ð·Ð¾Ð²

0.24

expl

0.24

WARDED

0.24

Activations Density 0.001%

business and legal text snippets

No Comments

No Known Activations