INDEX

Explanations

health or "/dev"

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

å¥Ķ

-0.30

iele

-0.27

rig

-0.27

ç«ĭè¶³

-0.26

çİ¯ç»ķ

-0.26

ç»µ

-0.26

è§¦

-0.24

_trace

-0.24

á½²

-0.24

åīĶ

-0.24

POSITIVE LOGITS

loth

0.27

ofi

0.26

@student

0.26

 whatsoever

0.25

olith

0.25

=length

0.25

 pháºŃn

0.25

éłĲ

0.25

Stamp

0.25

IKE

0.24

Activations Density 0.001%

health or "/dev"

No Comments

No Known Activations