INDEX

Explanations

Warren

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

usc

-0.27

ä¾

-0.25

should

-0.25

ach

-0.25

ç¼ĺ

-0.24

 Props

-0.24

SER

-0.24

elements

-0.24

 hero

-0.24

 front

-0.24

POSITIVE LOGITS

.lo

0.32

 loose

0.26

çĬĦ

0.26

å°±å¥½

0.25

entai

0.25

duo

0.25

lod

0.25

egt

0.25

æĿ¾

0.25

 Tits

0.24

Activations Density 0.014%

Warren

No Comments

No Known Activations