INDEX

Explanations

but

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

çºµæ¨ª

-0.28

æ²¤

-0.27

atial

-0.26

eker

-0.26

å¼¥

-0.26

çĸ¤

-0.26

 bureaucr

-0.25

 insurer

-0.25

okie

-0.24

TEX

-0.24

POSITIVE LOGITS

ãģ£ãģ¡ãĤĥ

0.30

anza

0.28

ton

0.26

eres

0.25

planation

0.25

æī¹åĩĨ

0.24

nf

0.24

 Calc

0.24

Jacob

0.24

ä»¤äºº

0.24

Activations Density 0.010%

but

No Comments

No Known Activations