INDEX

Explanations

CD

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

entifier

-0.28

*č↵

-0.25

 calculation

-0.24

insula

-0.24

PTY

-0.24

rite

-0.24

ç®Ĺ

-0.24

 Placeholder

-0.23

 Rome

-0.23

raid

-0.23

POSITIVE LOGITS

Eyl

0.28

 Governors

0.27

.Msg

0.26

æıĲåıĬ

0.26

band

0.25

çĽ¸åħ³

0.25

bel

0.24

ãĥ³ãĤ°

0.24

=E

0.24

åĪĽæĸ°

0.24

Activations Density 2.096%

CD

No Comments

No Known Activations