INDEX

Explanations

scientific/medical texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 summaries

-0.27

 grand

-0.27

 Christie

-0.27

FOX

-0.26

omorphic

-0.25

å¥½çİ©

-0.25

çĤİ

-0.25

ENSE

-0.24

vre

-0.24

åĪ¨

-0.24

POSITIVE LOGITS

ongan

0.27

upt

0.26

åı®

0.25

éĩĳå±±

0.25

ought

0.25

åħ¹

0.24

æĮ£æīİ

0.24

FileDialog

0.24

çļĦåĬªåĬĽ

0.24

çĽ®

0.24

Activations Density 0.006%

scientific/medical texts

No Comments

No Known Activations