INDEX

Explanations

Hive questions or Bee Hives

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

isson

-0.26

Ð¾ÑģÑĤ

-0.26

æĥ³åĥı

-0.25

 accumulator

-0.25

Accessor

-0.24

rosso

-0.24

atter

-0.24

akan

-0.24

 grief

-0.23

 Accum

-0.23

POSITIVE LOGITS

uese

0.28

æ°ĳæĶ¿

0.26

rous

0.26

ordes

0.25

fan

0.25

aldi

0.25

aes

0.24

ADE

0.24

 pitched

0.24

mando

0.23

Activations Density 0.004%

Hive questions or Bee Hives

No Comments

No Known Activations