INDEX

Explanations

oll

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

.cleaned

-0.28

 Sims

-0.27

 PANEL

-0.27

cased

-0.26

 Panel

-0.26

ollapse

-0.26

 Musical

-0.26

 panel

-0.25

panel

-0.25

cff

-0.25

POSITIVE LOGITS

áº¡n

0.26

arda

0.26

å¯¹æīĭ

0.25

åī¯

0.25

ç´Ĳ

0.24

datasets

0.24

uvian

0.23

åĮĹå¤§

0.23

setDefault

0.23

.onError

0.23

Activations Density 0.003%

oll

No Comments

No Known Activations