INDEX

Explanations

trauma

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

åĲĮå¿ĥ

-0.27

 Concent

-0.25

 concent

-0.25

 ÄĳÃ¢u

-0.25

 sobie

-0.24

 rÃ³Å¼ne

-0.24

å·¥ç¨ĭè´¨éĩı

-0.24

<<<

-0.24

æľīèī²

-0.24

 Sticky

-0.23

POSITIVE LOGITS

fuse

0.27

ot

0.26

 handing

0.24

oku

0.23

jal

0.23

uter

0.23

pheres

0.23

pit

0.23

FUN

0.23

Âł

0.23

Activations Density 35.123%

trauma

No Comments

No Known Activations