INDEX

Explanations

aside

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

 astr

-0.27

 standing

-0.27

 sÃŃ

-0.26

Aub

-0.25

SingleNode

-0.24

standing

-0.24

ÑģÑĤÐ°Ð½Ð°Ð²

-0.24

 stood

-0.24

acional

-0.24

cup

-0.23

POSITIVE LOGITS

 TSRMLS

0.26

ÑĤÐ°Ð½

0.26

 hooks

0.25

 fetched

0.25

omez

0.25

 Hooks

0.25

ISTA

0.24

ahas

0.24

æıŃ

0.24

ieres

0.24

Activations Density 22.129%

aside

No Comments

No Known Activations