INDEX

Explanations

rist

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

 ÐºÑĢÐ°Ð¹

-0.25

ILITY

-0.25

CEPTION

-0.25

Pretty

-0.24

ë¦Ħ

-0.24

opian

-0.24

amide

-0.24

.TabStop

-0.24

 fian

-0.24

 vigor

-0.24

POSITIVE LOGITS

äºīå¤º

0.30

afa

0.28

theses

0.27

BRE

0.27

phinx

0.25

icom

0.25

-ignore

0.24

htm

0.24

å¢ŀ

0.24

âİ

0.24

Activations Density 0.238%

rist

No Comments

No Known Activations