INDEX

Explanations

say "http word"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

er

-0.29

Ø©

-0.27

å¤ł

-0.26

ties

-0.25

ìķ¼

-0.24

ity

-0.23

 Âł

-0.23

htag

-0.23

×Ķ

-0.23

hold

-0.23

POSITIVE LOGITS

ening

0.29

Ð¾Ð³ÑĢÐ°Ð¼

0.25

ally

0.24

 interception

0.23

aries

0.23

æĭ¦æĪª

0.23

STER

0.22

@\

0.22

_ALIAS

0.22

ãģ®ãģ¯

0.22

Activations Density 1.323%

say "http word"

No Comments

No Known Activations