INDEX

Explanations

evolution

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

tant

-0.32

egra

-0.30

opic

-0.30

ective

-0.28

anoi

-0.28

egal

-0.28

_RAW

-0.26

Lane

-0.26

endment

-0.25

anter

-0.25

POSITIVE LOGITS

comings

0.28

èľļ

0.28

rons

0.27

 incoming

0.26

è¯ģ

0.25

ä¹ĭæīĢ

0.25

æľµ

0.25

 ambiguous

0.25

æ»ħ

0.25

åŀĽ

0.25

Activations Density 0.451%

evolution

No Comments

No Known Activations